Biologically Plausible Connectionist Prediction of Natural Language Thematic Relations

Author(s)

Garcia Rosa, Joao Luis ^[1] ; Adan-Coello, Juan Manuel ^[2]

Affiliation

^[1] Univ Sao Paulo, Dept Comp Sci, NILC Interinst Ctr Res & Dev Computat Linguist, Sao Carlos, SP - Brazil

^[2] Pontifical Catholic Univ Campinas, Comp Engn Fac, Campinas, SP - Brazil

• Document type: Journal article
• Source: JOURNAL OF UNIVERSAL COMPUTER SCIENCE; v. 16, n. 21, p. 3245-3277, 2010.
• Web of Science Citations: 0

Abstract

In Natural Language Processing (NLP) symbolic systems, several linguistic phenomena, for instance, the thematic role relationships between sentence constituents, such as AGENT, PATIENT, and LOCATION, can be accounted for by the employment of a rule-based grammar. Another approach to NLP concerns the use of the connectionist model, which has the benefits of learning, generalization and fault tolerance, among others. A third option merges the two previous approaches into a hybrid one: a symbolic thematic theory is used to supply the connectionist network with initial knowledge. Inspired on neuroscience, it is proposed a symbolic-connectionist hybrid system called BIO theta PRED (BIOlogically plausible thematic (theta) symbolic-connectionist PREDictor), designed to reveal the thematic grid assigned to a sentence. Its connectionist architecture comprises, as input, a featural representation of the words (based on the verb/noun WordNet classification and on the classical semantic microfeature representation), and, as output, the thematic grid assigned to the sentence. BIO theta PRED is designed to ``predict{''} thematic (semantic) roles assigned to words in a sentence context, employing biologically inspired training algorithm and architecture, and adopting a psycholinguistic view of thematic theory. (AU)

• FAPESP's process: 08/08245-4 - Use of machine learning techniques and Computational Linguistics to text treatment
• Grantee: João Luís Garcia Rosa
• Support Opportunities: Regular Research Grants